한국정보과학회논문지:소프트웨어및응용 (Journal of KIISE:Software and Applications)

한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지

다중 인식기의 다단계 결합을 통한 무제약 필기숫자 인식

Unconstrained Handwritten Numeral Recognition using Multistage Combination of Multiple Recognizers

  • 발행 : 1999.01.01

⟨ 이전 논문 다음 논문 ⟩

초록

Researches on digit recognition have been conducted actively for a long time because the classes to recognize are much fewer than other character sets and because it is very likely thatthe digit recognition can be applied to many problems in real world, The recent studies on designingrecognition system with high performance are in progress with two different aspects. One is toconstruct a recognizer using several features at the same time, and the other is to use severalrecognizers. In this paper, we propose a multistage combination method to recognize the unconstrainedhandwritten numerals. The method is a two-stage combination method which uses multiplecombination methods at the same time unlike the existing methods with only one combination method.The recognizers are first combined by several combination methods of different classes simultaneously,and then the results of them are combined by another combination method to generate a final result.Five recognizers and eight combination methods are used in the proposed system. The experimentalresults showed that the recognition rates on CENPARMI and CEDAR data were 97.75% and 98.6%,respectively and the recognition performance could be improved as the process passed through stages,We could get the best performance by combining the combination methods of different classes, whichmeans there are a complementary relation among them, The proposed method can be considered asan extended version of the existing combination methods.

키워드

참고문헌

  1. Proceedings of 2nd ICDAR State of the Art of Handwritten Numeral Recognition in Japan-The Results of the First IPTP Character Recognition Competition T.Matsui;T.Noumi;I.Yamashita;T.Wakahara;M.Yoshimuro
  2. Proceedings of 4th IWFHR Result of Second IPTP Character Recognition Competition and Studies on Multi-Expert Handwritten Numeral Recognition T.Noumi;T.Matsui;I.Yamashita;
  3. 한국정보과학회지 v.14 no.4 다중 인식기의 결합 방법 - 연구사례조사 백종현;조성배;이일병
  4. Computer Vision and shape Recoginiton Contour Tracing and Parametric Approximations for Digitized Patterns R.Legault;C.Y.Suen
  5. IEEE Trans.on System, Man and Cybernetics v.20 A Generalized Knowledge-Based System for the Recognition of Unconstrained Handwritten Numerials T.Mai;C.Y.Suen
  6. Proceedings of 1st IWFHR Unconstrained Handwritten Character Classification Using Modified Backpropagation Model A.Krzyzak;W.Dai;C.Y.Suen
  7. IEEE Trans. on Pattern Recognition and Machine Intelligence v.18 no.6 Off-Line Recognition of Totally Unconstrained Handwritten Numerals Using Multilayer Cluster Neural Network Seong-Whan Lee
  8. 한국정보과학회 봄 학술발표논문집 이중 결합 구조를 갖는 다중 인식기 시스템 백종현;조성배;이관용;이일병
  9. Journal of Pattern Recognition and Artificial Intelligence v.5 no.1/2 Understanding Handwritten Text in a Structured Environment: Determining ZIP Codes from Addreses E,Cohen;J.J.Hull;S.N.Srihari
  10. Proceedings of 3rd IWFHR Handprinted Digit Recognition : A Comparison of Algorithms D.-S.Lee;S.N.Srihari
  11. Recognition of Unconstrained Handwritten Numerals Based on Dual Cooperative Neural Network Y.Choi
  12. Proceedings of 1st IWFHR Constrained Neural Networks for Unconstrained Handwrittern Digit Recognition Y.LeCun (et al.)
  13. IEEE Trans,on Neural Networks v.3 no.6 Handwritten Digit Recognition by Neural Networks with Single Layer Training S.Knerr;L.Personnaz;G.Dreyfus
  14. Proceedings of IJCNN Handwritten Digit Rcognition with principal component analysis and radial basis function G.Deco;R.Blasig
  15. Proceedings of World Congress on Neural Networks v.1 Recognition of Handwritten Numerals using Optimized Prototypes H.Yan
  16. Proceedings of World Congress on Neural Networks v.3 A Modular Cyclic Neural Network for Character Recognition M.Costa;E.Filippi;E.Pasero
  17. Proceedings of 4th IWFHR Combination of Stroke/Background Structure and Contour-direction Features in Handprinted Alphanumeric Recognition T.Matsui;T.Tsutsumida;S.N.Srihari
  18. Proceedings of IJCNN Recognition of Handwritten Numeric Characters using Neural Networks Designed on Approximate Reasoning architecture Y.Kojima (et al.)
  19. Proceedings of 2nd ICDAR Practical Implementation of a Radial Basis Function Network for handwritten Digit Recognition B.Lemarie
  20. IEEE Trans. on System, Man and Cybernetics v.22 no.3 Methods of Combining Multiple Classifiers and Their Applications to handwriting Recognition L.Xu;A.Krzyzak;C.Y.Suen
  21. Proceedings of 3rd IWFHR An Optimal Method of Combining Multiple Classifiers for Unconstrained Hand Written Numeral Recognition Y.S.Huang;C.Y.Suen